Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 21 for “"embedding models"”.
-
AWE: Attention Word Embedding
Word embedding models learn semantically rich vector representations of words and are widely used to initialize natural processing language (NLP) models. The popular continuous bag-of-words (CBOW) model of word2vec learns a vector embedding by masking a given word in a sentence and then using the …
-
Methods for Latent Space Interpretation via In-the-loop Fine-Tuning
With language models increasing exponentially in scale, being able to interpret and justify model outputs is an area of increasing interest. Although enhancing the performance of these models in chat mediums has been the focus of interaction with AI, the visualization of model latent space offers a …
-
Clustering Tweets via Tweet Embeddings
… users and their interests. We consider various embedding models to produce tweet embeddings, which we then use to cluster the tweets, forming groups of semantically similar tweets. We then compare these tweet clusters to users clustered by interest based on accounts they follow. This work …
-
Summarizing Developer Chat Conversations
… primary topics discussed. We evaluate different embedding models and study their impact on the performance of the topic modeling technique. We perform an extensive analysis of the topics per month and also study evolution of the topics over a period of one year.
-
Log file anomaly detection using knowledge graphs and graph neural networks
… normal behavior. The second component applies KG embedding models enhanced with GNN layers to the generated KG and employs KGC to determine suspiciousness of new information through binary classification. We evaluated the proposed method using two public datasets with standard KGC metrics. The …
-
Software Requirements Classification Using Word Embeddings and Convolutional Neural Networks
… classification, specifically the use of word embeddings for document representation when training a convolutional neural network (CNN). As past research endeavors mainly utilize information retrieval and traditional machine learning techniques, we entertain the potential of deep learning on …
-
A Study on Leveraging Generative Artificial Intelligence and Text Clustering to Support Vendors
… also recommends continued exploration in embedding models and RAG framework to enhance feedback quality and information retrieval. The potential to integrate generative AI tools within Amazon Last Mile represents an underexplored opportunity for significant enhancements in efficiency, …
-
Deep Learning for Unstructured Data by Leveraging Domain Knowledge
… problem in the text mining domain, i.e, embedding of rare and out-of-vocabulary (OOV) words, by refining word embedding models and character embedding models in an iterative way. We illustrate the simplicity but effectiveness of our method when applying it to online professional profiles …
-
Deep concept reasoning: beyond the accuracy-interpretability trade-off
… almost as fast as they find flaws in their models. Although deep learning models can achieve superhuman performances, explaining deep learning decisions and mistakes is often impossible even for "explainable AI" specialists, causing lawmakers to question the ethical and legal ramifications …
-
Interpretable semantic representations from neural language models and computer vision
… linguistics is dominated by high capacity neural models that in many cases outperform even human baselines on a wide variety of language-based tasks. However, a serious drawback to the development of these semantic models is in the ambiguity of these representations, as the dimensions of these …
-
Agentic Framework for Domain-specific RAG Evaluation
Large Language Models (LLMs) have revolutionized generation and understanding of textual information and have wide-ranging applications. While the capabilities of LLMs are immediately impressive to any user, extended use quickly reveals problems of inaccurate text generation associated with these …
-
Enriching Knowledge Graphs Using Machine Learning Techniques
… and classes. FoodKG employs an existing graph embedding technique trained on a controlled vocabulary called AGROVOC, which is published by the Food and Agriculture Organization of the United Nations. AGROVOC includes terms and classes in the agriculture and food domains. As a result, FoodKG can …
-
Cohering with the Crowd: How Audiences Shape the Quasi-Scientific Process of Entrepreneurship
… validate an empirical framework that uses word embedding models to study theoretical coherence and find that theoretical coherence is able to explain the appeal of product-category combinations not easily addressed by prototype theory. The second essay examines why successful experimentation …
-
The Evolution of Topological Concepts in Online Social Networks
… that can be used to train supervised learning models. Lastly, the data arrives in a stream which requires compressed representations for historic data and the ability to handle changes in the relationships present in the data over time. This thesis addresses the challenges of modelling evolving …
-
Question Answering on Dynamic Knowledge Graph for Chemistry
… structure, the semantic heterogeneity, the embedding of numerical values, and the large scale of the chemistry Knowledge Graph. The thesis studied the two main methods for Knowledge Graph Question Answering: the Semantic Parsing and Knowledge Graph embedding methods against the chemistry …
-
Data-driven and Machine Learning approaches for exploration and inference of Biological Pathways in physiological and pathological states
… changes in cancer through machine learning models that classify cancer types and subtypes. Interpretation of these models through pathway analysis techniques confirms that the genomic loci they detect are involved in cancer processes. Despite the central importance and broad applicability of …
-
Help Wanted: Robust Concept Interventions for Interpretable Deep Neural Networks
… concludes. This myopic paradigm prevents models from soliciting or benefiting from external guidance when it matters most. In contrast, humans routinely consult one another, ask for help, and incorporate new evidence on the fly. This thesis asks: how can we design DNNs that capitalise on …
-
Efficiently Searching for Objects Within Large Collections of Images and Video
… is used to train object detection and tracking models for autonomous driving systems [82], to annotate map datasets such as OpenStreetMap with locations of traffic lights, stop signs, and other infrastructure [59]; and to automate insurance claims processing by analyzing collision scene footage …
-
Enriching Word Representation Learning for Affect Detection and Affect-Aware Recommendations
… one by effective pre-processing of training word embeddings and second by incorporating both affective and contextual features deeply into text representations. We demonstrate the benefits of enriched word representations in both affect detection and affect-aware recommendation tasks. This …
-
Hybrid Words Representation for the classification of low quality text
… of the main issues is that the traditional word embeddings are unable to capture polysemy (assigns the same representation of a word irrespective of its context and meaning) and out of vocabulary words (assigns a random representation). Furthermore, traditional word embeddings fail to capture …
Page 1 of 2